Training-Ready RL Environments + Evals

Verifiers for LLM Reinforcement Learning

Collection of evals for Inspect AI

AndroidWorld is an environment and benchmark for autonomous agents.

A privacy-first, open-source platform for knowledge management and collaboration. Download link: http://github.com/logseq/logseq/releases. roadmap: http://trello.com/b/8txSM12G/roadmap

Model Context Protocol Servers

♨️ Warming up TikTok accounts, one swipe at a time

The open source Firebase alternative.

Enhanced ChatGPT Clone: Features Agents, DeepSeek, Anthropic, AWS, OpenAI, Assistants API, Azure, Groq, o1, GPT-4o, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message se…

Letting Claude Code develop his own MCP tools :)

MTEB: Massive Text Embedding Benchmark

Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)

All-in-one infrastructure for search, recommendations, RAG, and analytics offered via API

A course on aligning smol models.

Composio equips agents with well-crafted tools empowering them to tackle complex tasks

Block users who loves a specific tweet, and help you improve your experience using Twitter.

A database of SDKs, frameworks, libraries, and tools for creating, monitoring, debugging and deploying autonomous AI agents

Train a language model to answer WhatsApp messages as you.